#include <linux/nvme_ioctl.h>
#include <linux/t10-pi.h>
#include <linux/pm_qos.h>
-#include <scsi/sg.h>
#include <asm/unaligned.h>
#include "nvme.h"
MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O");
EXPORT_SYMBOL_GPL(nvme_io_timeout);
-unsigned char shutdown_timeout = 5;
+static unsigned char shutdown_timeout = 5;
module_param(shutdown_timeout, byte, 0644);
MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown");
module_param(force_apst, bool, 0644);
MODULE_PARM_DESC(force_apst, "allow APST for newly enumerated devices even if quirked off");
+static bool streams;
+module_param(streams, bool, 0644);
+MODULE_PARM_DESC(streams, "turn on support for Streams write directives");
+
struct workqueue_struct *nvme_wq;
EXPORT_SYMBOL_GPL(nvme_wq);
static struct class *nvme_class;
+int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
+{
+ if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
+ return -EBUSY;
+ if (!queue_work(nvme_wq, &ctrl->reset_work))
+ return -EBUSY;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nvme_reset_ctrl);
+
+static int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
+{
+ int ret;
+
+ ret = nvme_reset_ctrl(ctrl);
+ if (!ret)
+ flush_work(&ctrl->reset_work);
+ return ret;
+}
+
static blk_status_t nvme_error_status(struct request *req)
{
switch (nvme_req(req)->status & 0x7ff) {
}
EXPORT_SYMBOL_GPL(nvme_alloc_request);
+static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable)
+{
+ struct nvme_command c;
+
+ memset(&c, 0, sizeof(c));
+
+ c.directive.opcode = nvme_admin_directive_send;
+ c.directive.nsid = cpu_to_le32(0xffffffff);
+ c.directive.doper = NVME_DIR_SND_ID_OP_ENABLE;
+ c.directive.dtype = NVME_DIR_IDENTIFY;
+ c.directive.tdtype = NVME_DIR_STREAMS;
+ c.directive.endir = enable ? NVME_DIR_ENDIR : 0;
+
+ return nvme_submit_sync_cmd(ctrl->admin_q, &c, NULL, 0);
+}
+
+static int nvme_disable_streams(struct nvme_ctrl *ctrl)
+{
+ return nvme_toggle_streams(ctrl, false);
+}
+
+static int nvme_enable_streams(struct nvme_ctrl *ctrl)
+{
+ return nvme_toggle_streams(ctrl, true);
+}
+
+static int nvme_get_stream_params(struct nvme_ctrl *ctrl,
+ struct streams_directive_params *s, u32 nsid)
+{
+ struct nvme_command c;
+
+ memset(&c, 0, sizeof(c));
+ memset(s, 0, sizeof(*s));
+
+ c.directive.opcode = nvme_admin_directive_recv;
+ c.directive.nsid = cpu_to_le32(nsid);
+ c.directive.numd = sizeof(*s);
+ c.directive.doper = NVME_DIR_RCV_ST_OP_PARAM;
+ c.directive.dtype = NVME_DIR_STREAMS;
+
+ return nvme_submit_sync_cmd(ctrl->admin_q, &c, s, sizeof(*s));
+}
+
+static int nvme_configure_directives(struct nvme_ctrl *ctrl)
+{
+ struct streams_directive_params s;
+ int ret;
+
+ if (!(ctrl->oacs & NVME_CTRL_OACS_DIRECTIVES))
+ return 0;
+ if (!streams)
+ return 0;
+
+ ret = nvme_enable_streams(ctrl);
+ if (ret)
+ return ret;
+
+ ret = nvme_get_stream_params(ctrl, &s, 0xffffffff);
+ if (ret)
+ return ret;
+
+ ctrl->nssa = le16_to_cpu(s.nssa);
+ if (ctrl->nssa < BLK_MAX_WRITE_HINTS - 1) {
+ dev_info(ctrl->device, "too few streams (%u) available\n",
+ ctrl->nssa);
+ nvme_disable_streams(ctrl);
+ return 0;
+ }
+
+ ctrl->nr_streams = min_t(unsigned, ctrl->nssa, BLK_MAX_WRITE_HINTS - 1);
+ dev_info(ctrl->device, "Using %u streams\n", ctrl->nr_streams);
+ return 0;
+}
+
+/*
+ * Check if 'req' has a write hint associated with it. If it does, assign
+ * a valid namespace stream to the write.
+ */
+static void nvme_assign_write_stream(struct nvme_ctrl *ctrl,
+ struct request *req, u16 *control,
+ u32 *dsmgmt)
+{
+ enum rw_hint streamid = req->write_hint;
+
+ if (streamid == WRITE_LIFE_NOT_SET || streamid == WRITE_LIFE_NONE)
+ streamid = 0;
+ else {
+ streamid--;
+ if (WARN_ON_ONCE(streamid > ctrl->nr_streams))
+ return;
+
+ *control |= NVME_RW_DTYPE_STREAMS;
+ *dsmgmt |= streamid << 16;
+ }
+
+ if (streamid < ARRAY_SIZE(req->q->write_hints))
+ req->q->write_hints[streamid] += blk_rq_bytes(req) >> 9;
+}
+
static inline void nvme_setup_flush(struct nvme_ns *ns,
struct nvme_command *cmnd)
{
return BLK_STS_OK;
}
-static inline void nvme_setup_rw(struct nvme_ns *ns, struct request *req,
- struct nvme_command *cmnd)
+static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
+ struct request *req, struct nvme_command *cmnd)
{
+ struct nvme_ctrl *ctrl = ns->ctrl;
u16 control = 0;
u32 dsmgmt = 0;
+ /*
+ * If formated with metadata, require the block layer provide a buffer
+ * unless this namespace is formated such that the metadata can be
+ * stripped/generated by the controller with PRACT=1.
+ */
+ if (ns && ns->ms &&
+ (!ns->pi_type || ns->ms != sizeof(struct t10_pi_tuple)) &&
+ !blk_integrity_rq(req) && !blk_rq_is_passthrough(req))
+ return BLK_STS_NOTSUPP;
+
if (req->cmd_flags & REQ_FUA)
control |= NVME_RW_FUA;
if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD))
cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
+ if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams)
+ nvme_assign_write_stream(ctrl, req, &control, &dsmgmt);
+
if (ns->ms) {
switch (ns->pi_type) {
case NVME_NS_DPS_PI_TYPE3:
cmnd->rw.control = cpu_to_le16(control);
cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
+ return 0;
}
blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
break;
case REQ_OP_READ:
case REQ_OP_WRITE:
- nvme_setup_rw(ns, req, cmd);
+ ret = nvme_setup_rw(ns, req, cmd);
break;
default:
WARN_ON_ONCE(1);
if (nvme_keep_alive(ctrl)) {
/* allocation failure, reset the controller */
dev_err(ctrl->device, "keep-alive failed\n");
- ctrl->ops->reset_ctrl(ctrl);
+ nvme_reset_ctrl(ctrl);
return;
}
}
}
EXPORT_SYMBOL_GPL(nvme_stop_keep_alive);
-int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
+static int nvme_identify_ctrl(struct nvme_ctrl *dev, struct nvme_id_ctrl **id)
{
struct nvme_command c = { };
int error;
return nvme_submit_sync_cmd(dev->admin_q, &c, ns_list, 0x1000);
}
-int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid,
+static int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid,
struct nvme_id_ns **id)
{
struct nvme_command c = { };
return error;
}
-int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid,
- void *buffer, size_t buflen, u32 *result)
-{
- struct nvme_command c;
- union nvme_result res;
- int ret;
-
- memset(&c, 0, sizeof(c));
- c.features.opcode = nvme_admin_get_features;
- c.features.nsid = cpu_to_le32(nsid);
- c.features.fid = cpu_to_le32(fid);
-
- ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &res, buffer, buflen, 0,
- NVME_QID_ANY, 0, 0);
- if (ret >= 0 && result)
- *result = le32_to_cpu(res.u32);
- return ret;
-}
-
-int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
+static int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11,
void *buffer, size_t buflen, u32 *result)
{
struct nvme_command c;
return ret;
}
-int nvme_get_log_page(struct nvme_ctrl *dev, struct nvme_smart_log **log)
-{
- struct nvme_command c = { };
- int error;
-
- c.common.opcode = nvme_admin_get_log_page,
- c.common.nsid = cpu_to_le32(0xFFFFFFFF),
- c.common.cdw10[0] = cpu_to_le32(
- (((sizeof(struct nvme_smart_log) / 4) - 1) << 16) |
- NVME_LOG_SMART),
-
- *log = kmalloc(sizeof(struct nvme_smart_log), GFP_KERNEL);
- if (!*log)
- return -ENOMEM;
-
- error = nvme_submit_sync_cmd(dev->admin_q, &c, *log,
- sizeof(struct nvme_smart_log));
- if (error)
- kfree(*log);
- return error;
-}
-
int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
{
u32 q_count = (*count - 1) | ((*count - 1) << 16);
* access to the admin queue, as that might be only way to fix them up.
*/
if (status > 0) {
- dev_err(ctrl->dev, "Could not set queue count (%d)\n", status);
+ dev_err(ctrl->device, "Could not set queue count (%d)\n", status);
*count = 0;
} else {
nr_io_queues = min(result & 0xffff, result >> 16) + 1;
return nvme_user_cmd(ns->ctrl, ns, (void __user *)arg);
case NVME_IOCTL_SUBMIT_IO:
return nvme_submit_io(ns, (void __user *)arg);
-#ifdef CONFIG_BLK_DEV_NVME_SCSI
- case SG_GET_VERSION_NUM:
- return nvme_sg_get_version_num((void __user *)arg);
- case SG_IO:
- return nvme_sg_io(ns, (void __user *)arg);
-#endif
default:
#ifdef CONFIG_NVM
if (ns->ndev)
static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
- switch (cmd) {
- case SG_IO:
- return -ENOIOCTLCMD;
- }
return nvme_ioctl(bdev, mode, cmd, arg);
}
#else
}
#endif /* CONFIG_BLK_DEV_INTEGRITY */
+static void nvme_set_chunk_size(struct nvme_ns *ns)
+{
+ u32 chunk_size = (((u32)ns->noiob) << (ns->lba_shift - 9));
+ blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(chunk_size));
+}
+
static void nvme_config_discard(struct nvme_ns *ns)
{
struct nvme_ctrl *ctrl = ns->ctrl;
BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
NVME_DSM_MAX_RANGES);
- ns->queue->limits.discard_alignment = logical_block_size;
- ns->queue->limits.discard_granularity = logical_block_size;
+ if (ctrl->nr_streams && ns->sws && ns->sgs) {
+ unsigned int sz = logical_block_size * ns->sws * ns->sgs;
+
+ ns->queue->limits.discard_alignment = sz;
+ ns->queue->limits.discard_granularity = sz;
+ } else {
+ ns->queue->limits.discard_alignment = logical_block_size;
+ ns->queue->limits.discard_granularity = logical_block_size;
+ }
blk_queue_max_discard_sectors(ns->queue, UINT_MAX);
blk_queue_max_discard_segments(ns->queue, NVME_DSM_MAX_RANGES);
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
{
struct nvme_ns *ns = disk->private_data;
+ struct nvme_ctrl *ctrl = ns->ctrl;
u16 bs;
/*
if (ns->lba_shift == 0)
ns->lba_shift = 9;
bs = 1 << ns->lba_shift;
+ ns->noiob = le16_to_cpu(id->noiob);
blk_mq_freeze_queue(disk->queue);
- if (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)
+ if (ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)
nvme_prep_integrity(disk, id, bs);
blk_queue_logical_block_size(ns->queue, bs);
+ if (ns->noiob)
+ nvme_set_chunk_size(ns);
if (ns->ms && !blk_get_integrity(disk) && !ns->ext)
nvme_init_integrity(ns);
if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk))
else
set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
- if (ns->ctrl->oncs & NVME_CTRL_ONCS_DSM)
+ if (ctrl->oncs & NVME_CTRL_ONCS_DSM)
nvme_config_discard(ns);
blk_mq_unfreeze_queue(disk->queue);
}
int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl)
{
- unsigned long timeout = SHUTDOWN_TIMEOUT + jiffies;
+ unsigned long timeout = jiffies + (shutdown_timeout * HZ);
u32 csts;
int ret;
}
if (force_apst && (ctrl->quirks & NVME_QUIRK_NO_DEEPEST_PS)) {
- dev_warn(ctrl->dev, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n");
+ dev_warn(ctrl->device, "forcibly allowing all power states due to nvme_core.force_apst -- use at your own risk\n");
ctrl->quirks &= ~NVME_QUIRK_NO_DEEPEST_PS;
}
prev_apsta = ctrl->apsta;
if (ctrl->quirks & NVME_QUIRK_NO_APST) {
if (force_apst && id->apsta) {
- dev_warn(ctrl->dev, "forcibly allowing APST due to nvme_core.force_apst -- use at your own risk\n");
+ dev_warn(ctrl->device, "forcibly allowing APST due to nvme_core.force_apst -- use at your own risk\n");
ctrl->apsta = 1;
} else {
ctrl->apsta = 0;
ret = -EINVAL;
if (!ctrl->opts->discovery_nqn && !ctrl->kas) {
- dev_err(ctrl->dev,
+ dev_err(ctrl->device,
"keep-alive support is mandatory for fabrics\n");
ret = -EINVAL;
}
dev_pm_qos_hide_latency_tolerance(ctrl->device);
nvme_configure_apst(ctrl);
+ nvme_configure_directives(ctrl);
ctrl->identified = true;
return nvme_dev_user_cmd(ctrl, argp);
case NVME_IOCTL_RESET:
dev_warn(ctrl->device, "resetting controller\n");
- return ctrl->ops->reset_ctrl(ctrl);
+ return nvme_reset_ctrl_sync(ctrl);
case NVME_IOCTL_SUBSYS_RESET:
return nvme_reset_subsystem(ctrl);
case NVME_IOCTL_RESCAN:
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
int ret;
- ret = ctrl->ops->reset_ctrl(ctrl);
+ ret = nvme_reset_ctrl_sync(ctrl);
if (ret < 0)
return ret;
return count;
}
static DEVICE_ATTR(wwid, S_IRUGO, wwid_show, NULL);
+static ssize_t nguid_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
+ return sprintf(buf, "%pU\n", ns->nguid);
+}
+static DEVICE_ATTR(nguid, S_IRUGO, nguid_show, NULL);
+
static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
- return sprintf(buf, "%pU\n", ns->nguid);
+
+ /* For backward compatibility expose the NGUID to userspace if
+ * we have no UUID set
+ */
+ if (uuid_is_null(&ns->uuid)) {
+ printk_ratelimited(KERN_WARNING
+ "No UUID available providing old NGUID\n");
+ return sprintf(buf, "%pU\n", ns->nguid);
+ }
+ return sprintf(buf, "%pU\n", &ns->uuid);
}
static DEVICE_ATTR(uuid, S_IRUGO, uuid_show, NULL);
static struct attribute *nvme_ns_attrs[] = {
&dev_attr_wwid.attr,
&dev_attr_uuid.attr,
+ &dev_attr_nguid.attr,
&dev_attr_eui.attr,
&dev_attr_nsid.attr,
NULL,
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
if (a == &dev_attr_uuid.attr) {
+ if (uuid_is_null(&ns->uuid) ||
+ !memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
+ return 0;
+ }
+ if (a == &dev_attr_nguid.attr) {
if (!memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
return 0;
}
return ret;
}
+static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns)
+{
+ struct streams_directive_params s;
+ int ret;
+
+ if (!ctrl->nr_streams)
+ return 0;
+
+ ret = nvme_get_stream_params(ctrl, &s, ns->ns_id);
+ if (ret)
+ return ret;
+
+ ns->sws = le32_to_cpu(s.sws);
+ ns->sgs = le16_to_cpu(s.sgs);
+
+ if (ns->sws) {
+ unsigned int bs = 1 << ns->lba_shift;
+
+ blk_queue_io_min(ns->queue, bs * ns->sws);
+ if (ns->sgs)
+ blk_queue_io_opt(ns->queue, bs * ns->sws * ns->sgs);
+ }
+
+ return 0;
+}
+
static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
{
struct nvme_ns *ns;
blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
nvme_set_queue_limits(ctrl, ns->queue);
+ nvme_setup_streams_ns(ctrl, ns);
sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->instance);
if (nvme_nvm_ns_supported(ns, id) &&
nvme_nvm_register(ns, disk_name, node)) {
- dev_warn(ctrl->dev, "%s: LightNVM init failure\n", __func__);
+ dev_warn(ctrl->device, "%s: LightNVM init failure\n", __func__);
goto out_free_id;
}
mutex_lock(&ctrl->namespaces_mutex);
+ /* Forcibly unquiesce queues to avoid blocking dispatch */
+ blk_mq_unquiesce_queue(ctrl->admin_q);
+
/* Forcibly start all queues to avoid having stuck requests */
blk_mq_start_hw_queues(ctrl->admin_q);
revalidate_disk(ns->disk);
blk_set_queue_dying(ns->queue);
+ /* Forcibly unquiesce queues to avoid blocking dispatch */
+ blk_mq_unquiesce_queue(ns->queue);
+
/*
* Forcibly start all queues to avoid having stuck requests.
* Note that we must ensure the queues are not stopped
mutex_lock(&ctrl->namespaces_mutex);
list_for_each_entry(ns, &ctrl->namespaces, list) {
- blk_mq_start_stopped_hw_queues(ns->queue, true);
+ blk_mq_unquiesce_queue(ns->queue);
blk_mq_kick_requeue_list(ns->queue);
}
mutex_unlock(&ctrl->namespaces_mutex);
projects / linux / blobdiff